Nearest neighbor imputation of species-level, plot-scale forest structure attributes from LiDAR data

By Andrew Thomas Hudak, N. Crookston, Jeffrey Scott Evans, David E. Hall, Michael J. Falkowski. 2008

466 citations recorded by the source corpus.

Subfields: Ecology, Environmental Engineering, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/0ff8af4ba1c72425a955637d9069eddc02efb4bc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Environmental Engineering

In Nature and Landscape Conservation

Citations in the corpus

Non-parametric prediction and mapping of standing timber volume and biomass in a temperate forest: application of multiple optical/LiDAR-derived predictors (2010, methodology): “…basal area and tree height (Nieschulze, 2003; Packalén and Maltamo, 2006; Packalén and Maltamo, 2007; Nothdurft et al., 2009), recent studies, e.g. Hudak et al. (2008), Eskelson et al. (2009) and Vauhkonen et al. (2010), have shown that the RF approach generally produced better prediction results…”
Non-parametric prediction of diameter distributions using airborne laser scanner data (2009, background): “Alternatively, an importance value can be used to aid the final choice of predictors (Hudak et al., 2008).”
Comparison of nearest neighbour approaches for small area estimation of tree species-specific forest inventory attributes in central Europe using airborne laser scanner data (2010, methodology): “As opposed to Hudak et al. (2008a) who found that MSN and RF performed similarly well for the estimation of species specific basal area and tree density, we observed that MSN outperformed RF.”
A comparative analysis of kNN and decision tree methods for the Irish National Forest Inventory (2009, methodology): “( 2008 ) to impute forest structure attributes using field plot data and LiDAR derived canopy and topographic metrics.”
Variable selection strategies for nearest neighbor imputation methods used in remote sensing based forest inventory (2012, methodology): “Numerous distance metrics are used in NN imputation and many comparisons of them have been published recently (e.g., LeMay and Temesgen, 2005; Chirici et al., 2008; Hudak et al., 2008; Breidenbach et al., 2010; Latifi et al., 2010).”
Evaluation of most similar neighbour and random forest methods for imputing forest inventory variables using data from target and auxiliary stands (2012, methodology): “The general superiority of RF over conventional k-NN models has previously been stated by studies such as Vauhkonen et al. (2010) (for the single-tree method) and Hudak et al. (2008) and Latifi et al. (2010a) (for the area-based method).”
A best practices guide for generating forest inventory attributes from airborne laser scanning data using an area-based approach (2013, unknown): “, 2011) or non-parametric (e.g., Packalén and Maltamo 2007; Hudak et al. 2008; Frazer et al. 2011a; Järnstedt et al. 2012; Vastaranta et al. 2012) approaches.”
Comparison of small-footprint discrete return and full waveform airborne lidar data for estimating multiple forest variables (2016, methodology): “All points which intersected within field plot locations were 277 clipped from the dataset and used to create plot-level lidar variables, as in Falkowski et al. 278 (2009) and Hudak et al. (2008).”
Mapping vegetation morphology types in a dry savanna ecosystem: integrating hierarchical object-based image analysis with Random Forest (2014, background): “RF classification has been employed in environmental remote sensing for a variety of applications including land-cover mapping (Pal 2005; Sesnie et al. 2008), forest structural parameters, biomass estimation (Baccini et al. 2004, Hudak et al. 2008), and mapping of invasive Table 3.”